Menü
A systematic, evidence-based approach to finding and fixing bugs.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Plan, reason, and verify across multiple levels using multi-step reasoning, tree-of-thought, and structured agent workflows.
Detect and repair security vulnerabilities or operational errors in the agent's own code and environment without manual intervention.
Generate and apply complete design systems from text descriptions or visual examples using AI and modern tooling.
Adapt user interfaces automatically based on device, viewport, user preferences, and contextual signals.
Build and query knowledge graphs automatically to capture relationships between entities, concepts, and project artifacts.
Run agent tasks in isolated, sandboxed environments to prevent malicious or untrusted code from affecting the host system.
| name | debugging |
| description | A systematic, evidence-based approach to finding and fixing bugs. |
Category: Core Engineering Priority: Critical
A systematic, evidence-based approach to finding and fixing bugs.
Eliminate guesswork. Fix root causes, not symptoms.
Use this skill when:
Bug: Users see 500 error on checkout
1. Reproduce: Confirmed on staging with user ID 12345
2. Isolate: Error occurs in payment service, not cart service
3. Hypothesize: Null pointer when user has no saved cards
4. Test: Add debug log -> confirmed null `cards` array
5. Fix: Add null check before iterating cards
6. Verify: Checkout works for user 12345 AND existing users with cards
7. Regression test: Unit test for null cards scenario added
8. Document: Added to anti-patterns: "Always null-check before iteration"
Bug: 500 error
Fix: Added try-catch to swallow the error.